{"id":"https://openalex.org/W4306317422","doi":"https://doi.org/10.1145/3511808.3557678","title":"WDRASS: A Web-scale Dataset for Document Retrieval and Answer Sentence Selection","display_name":"WDRASS: A Web-scale Dataset for Document Retrieval and Answer Sentence Selection","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4306317422","doi":"https://doi.org/10.1145/3511808.3557678"},"language":"en","primary_location":{"id":"doi:10.1145/3511808.3557678","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3511808.3557678","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3511808.3557678","source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3511808.3557678","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100358738","display_name":"Zeyu Zhang","orcid":"https://orcid.org/0000-0002-7583-1867"},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeyu Zhang","raw_affiliation_strings":["University of Arizona, Tucson, AZ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Arizona, Tucson, AZ, USA","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056497976","display_name":"Thuy Vu","orcid":"https://orcid.org/0000-0003-1056-6975"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thuy Vu","raw_affiliation_strings":["Amazon Alexa AI, Manhattan Beach, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI, Manhattan Beach, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044136768","display_name":"Sunil Gandhi","orcid":"https://orcid.org/0000-0001-9493-2340"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sunil Gandhi","raw_affiliation_strings":["Amazon Alexa AI, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027218595","display_name":"Ankit Chadha","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ankit Chadha","raw_affiliation_strings":["Amazon Alexa AI, Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056376686","display_name":"Alessandro Moschitti","orcid":"https://orcid.org/0000-0003-2216-8034"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alessandro Moschitti","raw_affiliation_strings":["Amazon Alexa AI, Manhattan Beach, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI, Manhattan Beach, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5189,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.64081633,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4707","last_page":"4711"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13274","display_name":"Expert finding and Q&A systems","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8533724546432495},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.78093421459198},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6631314754486084},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6440455913543701},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5784986019134521},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5559925436973572},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5528969168663025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5400932431221008},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5138369202613831},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.47153908014297485},{"id":"https://openalex.org/keywords/open-domain","display_name":"Open domain","score":0.41246312856674194}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8533724546432495},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.78093421459198},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6631314754486084},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6440455913543701},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5784986019134521},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5559925436973572},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5528969168663025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5400932431221008},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5138369202613831},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.47153908014297485},{"id":"https://openalex.org/C2993776861","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Open domain","level":3,"score":0.41246312856674194},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3511808.3557678","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3511808.3557678","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3511808.3557678","source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.arizona.edu:10150/667202","is_oa":true,"landing_page_url":"http://hdl.handle.net/10150/667202","pdf_url":null,"source":{"id":"https://openalex.org/S4306400271","display_name":"UA Campus Repository (The University of Arizona)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I138006243","host_organization_name":"University of Arizona","host_organization_lineage":["https://openalex.org/I138006243"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"International Conference on Information and Knowledge Management, Proceedings","raw_type":"Proceedings"}],"best_oa_location":{"id":"doi:10.1145/3511808.3557678","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3511808.3557678","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3511808.3557678","source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8399999737739563,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4306317422.pdf","grobid_xml":"https://content.openalex.org/works/W4306317422.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W1966443646","https://openalex.org/W2086511124","https://openalex.org/W2108862644","https://openalex.org/W2251818205","https://openalex.org/W2618735189","https://openalex.org/W2767857566","https://openalex.org/W2912924812","https://openalex.org/W2963339397","https://openalex.org/W2963681593"],"related_works":["https://openalex.org/W2391533720","https://openalex.org/W2951097643","https://openalex.org/W4309395021","https://openalex.org/W3091989500","https://openalex.org/W3215363805","https://openalex.org/W204133468","https://openalex.org/W2991310128","https://openalex.org/W4307481286","https://openalex.org/W2395174199","https://openalex.org/W4226441484"],"abstract_inverted_index":{"Open-Domain":[0],"Question":[1],"Answering":[2],"(ODQA)":[3],"systems":[4,40],"generate":[5],"answers":[6,80],"from":[7,96],"relevant":[8],"text":[9],"returned":[10],"by":[11,103],"search":[12],"engines,":[13],"e.g.,":[14],"lexical":[15],"features-based":[16],"such":[17,22],"as":[18,23,78],"BM25,":[19],"or":[20],"embeddings-based":[21],"dense":[24],"passage":[25],"retrieval":[26,128],"(DPR).":[27],"Few":[28],"datasets":[29],"are":[30],"available":[31],"for":[32,66,81],"this":[33,59],"task:":[34],"they":[35],"mainly":[36],"focus":[37],"on":[38,42,53,69,106,115],"QA":[39,82,138],"based":[41,52,68],"machine":[43],"reading":[44],"(MR)":[45],"approach,":[46],"and":[47,89,93,108,129],"show":[48,120],"problematic":[49],"evaluation,":[50],"mostly":[51],"uncontextualized":[54],"short":[55],"answer":[56,70],"matching.":[57],"In":[58],"paper,":[60],"we":[61],"present":[62],"WDRASS,":[63],"a":[64],"dataset":[65,102,143],"ODQA":[67],"sentence":[71],"selection":[72],"(AS2)":[73],"models,":[74,131],"which":[75],"consider":[76],"sentences":[77,94],"candidate":[79],"systems.":[83],"WDRASS":[84,122],"consists":[85],"of":[86,127,136],"\u223c64k":[87],"questions":[88],"800k+":[90],"labeled":[91],"passages":[92],"extracted":[95],"30M":[97],"documents.":[98],"We":[99,140],"evaluate":[100],"the":[101,111,125,134],"training":[104],"models":[105,113],"it":[107],"comparing":[109],"with":[110],"same":[112],"trained":[114],"Google":[116],"NQ.":[117],"Our":[118],"experiments":[119],"that":[121],"significantly":[123],"improves":[124],"performance":[126],"reranking":[130],"thus":[132],"boosting":[133],"accuracy":[135],"downstream":[137],"tasks.":[139],"believe":[141],"our":[142],"can":[144],"produce":[145],"significant":[146],"impact":[147],"in":[148],"advancing":[149],"IR":[150],"research.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}